OB_FileTransfate/TranslationProcess.py

"""
	整理翻译文件，通过匹配翻译的excel表格，写入未翻译的字段
"""

import CoverProcess as func
import langconv

# 读取 excel
import xlrd
from xlrd.book import Book
from xlrd.sheet import Sheet
from xlrd.sheet import Cell

"""
基础配置文件
:param excellPath: 翻译excel表格路径
:param translationSheetName: 翻译表单名称
"""
isSave = True
excelPath = func.savePath + "/fanyi.xlsx"
translationSheetName = "翻译登记表" # 历史翻译【所有】/ 翻译登记表
baseLanguagePath = func.projectPath + "/YunPOS-iOS/YunPOS/language"

# 翻译文件路径
zhTransFilePath = func.savePath + "/aa.txt"

# 翻译文件路径
zhHansPath = baseLanguagePath + "/zh-Hans.lproj/Localizable.strings"
zhHantPath = baseLanguagePath + "/zh-Hant.lproj/Localizable.strings"
zhHKPath = baseLanguagePath + "/zh-HK.lproj/Localizable.strings"
enPath = baseLanguagePath + "/en.lproj/Localizable.strings"

# excel 暂存
global tmpExcelFile
tmpExcelFile = None
tmpExcelIndex = dict() # excel 索引

# 需要翻译的字段列表
global zhNeedList
zhNeedList = []

# 文件存储
global zhHansFile, zhHantFile, zhHKFile, enFile
global tmpStoreZhTrans
zhHansFile = [] # 简体中文
tmpStoreZhTrans = dict() # 简体中文

zhHantFile = [] # 繁体中文
zhHKFile = []   # 繁体中文
enFile = []     # 英文

global tmpNotNeedTransKeys
tmpNotNeedTransKeys = dict() # 不需要翻译的字段

# 判读 是否已经翻译了
# return: True 已经存在翻译；False 没有存在翻译；
def matchExcelTranslationToStr(aRow = []):
	zhValue = aRow[0]
	zhResult = func.findWordInFile(zhValue)
	if zhResult:
		for zh in zhResult:
			if "=" in zh:
				return True
	return False

# excel 相关
# 读取excel表格／获取翻译sheet表
def readExcelFile(excelPath, sheetName):
	excel = xlrd.open_workbook(excelPath)
	translation = excel.sheet_by_name(sheetName)
	return translation;

# 读入翻译文件至 缓存中
def readLanguageFilesToTmp():
	global zhHansFile, zhHantFile, zhHKFile, enFile
	global tmpStoreZhTrans, tmpNotNeedTransKeys

	# 中文简体
	zhHansFile = readFileNoReturn(zhHansPath)
	# 中文繁体
	zhHantFile = readFileNoReturn(zhHantPath)
	# 中文繁体
	zhHKFile = readFileNoReturn(zhHKPath)
	# 英文
	enFile = readFileNoReturn(enPath)

	# 中文简体暂存为 Dict，方便查询是否已经翻译了
	for zh in zhHansFile:
		key, value = removeTheTranslateLine(zh)
		if len(key) > 0:
			tmpStoreZhTrans[key] = value

	try:
		with open(func.savePath + "/NotNeedTrans.txt", "r", encoding="utf-8") as tFile:
			datas = tFile.read().splitlines()
			for str in datas:
				tmpNotNeedTransKeys[str] = "1"
	except IOError:
		print("File is not accessible.")

# 去除 引号，分号，空格，返回key，value 值
def removeTheTranslateLine(line = ""):
	if "=" not in line:
		return "", ""
	line = line.split(";")[0]

	result = line.split("=")

	tmpKey = ""
	tmpValue = ""
	if len(result) == 4:
		# 包含 = 的翻译
		tmpKey = result[0] + "=" + result[1]
		tmpValue = result[2] + "=" + result[3]
	elif len(result) == 3:
		tmpKey = result[0]
		tmpValue = result[1] + "=" + result[2]
	elif len(result) == 2:
		tmpKey = result[0]
		tmpValue = result[1]
	else:
		print("error")

	key = tmpKey.strip()
	value = tmpValue.strip()
	key = key.strip("\"")
	value = value.strip("\"")
	return key, value

# 读取文件，并去除换行符号
def readFileNoReturn(path):
	with open(path) as file:
		datas = file.read().splitlines()
		return datas
	return None


# 读取需要翻译的文件
def readNeedTranslationFile():
	global zhNeedList

	if True:
		tmpFile = open(zhTransFilePath, 'r', encoding="utf-8")
		zhNeedList = list(tmpFile)
		tmpFile.close()
	else:
		# 读取中文翻译文件
		func.readZhLocalizedFile()

		func.isReplace = True
		# 筛选需要翻译的数据
		subTranslateStr, subBeTranslateStr = func.search(func.dirPath)
		zhNeedList = subTranslateStr

# 去除首尾可能存在的空格
def dealStartEndSpace(str = ""):
	str = str.strip()
	return str

# 去除翻译文字\n 和 "
def dealStartEndChar(str = ""):
	str = str.strip("\n")
	str = str.strip("\"")
	return str

# 转换简体到繁体
def chsToCht(line):
	line = langconv.Converter('zh-hant').convert(line)
	line.encode('utf-8')
	return line

# 生成翻译文件 line
def createTranslateLine(zh, translate):
	return "\""+zh+"\""+" = "+"\""+translate+"\";";

"""
# 查看字段是否在excel中是否已经翻译
# return:   成功 返回 中文，英文，繁体
#           失败 Null
"""
def searchZhTranslationInExcel(zh = "", excel = excelPath, sheet = translationSheetName):
	global tmpExcelFile, tmpExcelIndex
	# 读入excel文件
	if tmpExcelFile == None:
		tmpExcelFile = readExcelFile(excel, sheet)
		tmpExcelIndex = createExcelIndexDict(tmpExcelFile)

	indexStr = tmpExcelIndex.get(zh)
	if indexStr != None:
		index = int(indexStr)

		row = tmpExcelFile.row_values(index)
		"""
		if (index > 1 and index < 2644) or (index > 2953):
			print(str(index) + "--匹配成功")
			enStr = dealStartEndSpace(row[1])
			if len(enStr) > 0:
				return zh, enStr, chsToCht(zh)
			else:
				print("--录入，但是未翻译：" + zh)
		"""
		print(str(index) + "--匹配成功")
		enStr = dealStartEndSpace(row[2])
		if len(enStr) > 0:
			return zh, enStr, chsToCht(zh)
		else:
			print("--录入，但是未翻译：" + zh)

	return zh, None, None

# 生成excel索引
def createExcelIndexDict(tmpExcelFile = []):
	tmpExcelIndex = dict()

	rowCount = 0  # 行数，<2644 行文件格式 "中文" "英文" "繁体" >2644 格式："None" "中文" "英文" "繁体" >2953 情况1
	spaceCount = 0  # 中间空行记录，最多10行，当>10就认为结束了
	for row in tmpExcelFile.get_rows():
		if (len(row[0].value) == 0 and len(row[1].value) == 0) or row[0].value == " ":
			spaceCount += 1
			if spaceCount > 10:
				break
			else:
				rowCount += 1
				continue
		"""
		if (rowCount > 1 and rowCount < 2644) or (rowCount > 2953):
			zhStr = dealStartEndSpace(row[0].value)
			tmpExcelIndex[zhStr] = str(rowCount)
		"""
		zhStr = dealStartEndSpace(row[1].value)
		tmpExcelIndex[zhStr] = str(rowCount)

		if len(row[1].value) > 0:
			spaceCount = 0
		rowCount += 1

	return tmpExcelIndex

"""
 写入翻译到 对应的翻译文件中去
 总共有4个翻译文件 -中文 -英文 -繁体 -繁体
"""
def writeTranslateToFile(zh, en, hk):
	zhStr = createTranslateLine(zh, zh)
	hkStr = createTranslateLine(zh, hk)
	enStr = createTranslateLine(zh, en)

	zhHansFile.append(zhStr)
	zhHantFile.append(hkStr)
	zhHKFile.append(hkStr)
	enFile.append(enStr)

	zh

	print("插入翻译: ", zhStr, enStr, hkStr)

# 写入翻译文件
def writeTmpToTrans():
	func.saveSetInPath(zhHansFile, zhHansPath)
	func.saveSetInPath(zhHantFile, zhHantPath)
	func.saveSetInPath(zhHKFile, zhHKPath)
	func.saveSetInPath(enFile, enPath)
	print("写入文件完成")

# 主运行
if __name__ == "__main__":
	# 读取文件缓存
	readNeedTranslationFile()
	readLanguageFilesToTmp()

	# 循环遍历需要翻译的字段
	zhNoTrans = set()
	for zhStr in zhNeedList:
		zhStr = dealStartEndChar(zhStr)
		zhNoTrans.add(zhStr)
		print("begin\n匹配：" + zhStr)
		zh, en, hk = searchZhTranslationInExcel(zhStr, excelPath, translationSheetName)
		if zh != None:
			if tmpStoreZhTrans.get(zh) == None:
				if en != None:
					writeTranslateToFile(zh, en, hk)
					zhNoTrans.remove(zhStr)
		print("---end\n")

	# 保存处理的文件
	func.saveSetInPath(zhNoTrans, zhTransFilePath)

	if isSave == True:
		writeTmpToTrans()
	# 结果
	#print("\n已经翻译：" + str(succCount) + "\n没有翻译：" + str(falureCount) + "\n总处理：" + str(rowCount))